Regularization in kernel learning
Under mild assumptions on the kernel, we obtain the best known error rates in a regularized learning scenario taking place in the corresponding reproducing kernel Hilbert space (RKHS). The main novelty in the analysis is a proof that one can use a regularization term that grows significantly slower than the standard quadratic growth in the RKHS norm.
|Collections||ANU Research Publications|
|Source:||The Annals of Statistics|
|01_Mendelson_Regularization_in_kernel_2010.pdf||Published Version||344.57 kB||Adobe PDF|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.